[Git][ghc/ghc][wip/T25560] 2 commits: rts: Determine max_n_capabilities at RTS startup
Ben Gamari (@bgamari)
gitlab at gitlab.haskell.org
Mon Dec 9 15:53:00 UTC 2024
Ben Gamari pushed to branch wip/T25560 at Glasgow Haskell Compiler / GHC
Commits:
bca74a7f by Ben Gamari at 2024-12-09T10:52:50-05:00
rts: Determine max_n_capabilities at RTS startup
Previously the maximum number of capabilities supported by the RTS was
statically capped at 256. However, this bound is uncomfortably low given
the size of today's machine.
While supporting unbounded, fully-dynamic adjustment would be nice, it
is complex and so instead we do something simpler: Probe the logical
core count at RTS startup and use this as the static bound for the rest
of our execution.
This should avoid users running into the capability limit on large
machines while avoiding wasting memory on a large capabilities array for
most users and keeping complexity at bay.
Addresses #25560.
- - - - -
8fdf194e by Ben Gamari at 2024-12-09T10:52:50-05:00
testsuite: Add test for #25560
- - - - -
10 changed files:
- docs/users_guide/using-concurrent.rst
- rts/Capability.c
- rts/Capability.h
- rts/RtsSymbols.c
- rts/Schedule.c
- rts/include/rts/Config.h
- rts/include/rts/Threads.h
- + testsuite/tests/rts/T25560.hs
- + testsuite/tests/rts/T25560.stderr
- testsuite/tests/rts/all.T
Changes:
=====================================
docs/users_guide/using-concurrent.rst
=====================================
@@ -157,8 +157,9 @@ use the RTS :rts-flag:`-N ⟨x⟩` options.
.. note::
The maximum number of capabilities supported by the GHC runtime system is
- determined when the compiler is built and currently defaults to 256
- capabilities.
+ determined when at RTS startup to be either 256, the value given by
+ :rts-flags:`-N ⟨x⟩`, or the number of logical CPU cores, whichever is
+ greater.
The following options affect the way the runtime schedules threads on
CPUs:
=====================================
rts/Capability.c
=====================================
@@ -16,6 +16,7 @@
*
* --------------------------------------------------------------------------*/
+#include "rts/Config.h"
#include "rts/PosixSource.h"
#include "Rts.h"
@@ -40,12 +41,16 @@ Capability MainCapability;
uint32_t n_capabilities = 0;
uint32_t enabled_capabilities = 0;
+// The size of the `capabilities` array initialized at RTS startup. Referenced
+// by GHC.Internal.Conc.Sync
+StgInt max_n_capabilities = MAX_N_CAPABILITIES;
+
// The array of Capabilities. It's important that when we need
// to allocate more Capabilities we don't have to move the existing
// Capabilities, because there may be pointers to them in use
// (e.g. threads in waitForCapability(), see #8209), so this is
// an array of Capability* rather than an array of Capability.
-Capability *capabilities[MAX_N_CAPABILITIES];
+Capability **capabilities;
// Holds the Capability which last became free. This is used so that
// an in-call has a chance of quickly finding a free Capability.
@@ -386,12 +391,30 @@ void initCapabilities (void)
}
#endif
- if (RtsFlags.ParFlags.nCapabilities > MAX_N_CAPABILITIES) {
- errorBelch("warning: this GHC runtime system only supports up to %d capabilities",
- MAX_N_CAPABILITIES);
- RtsFlags.ParFlags.nCapabilities = MAX_N_CAPABILITIES;
+ /*
+ * Note [Capabilities array sizing]
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * Determine the size of the capabilities array as the maximum of:
+ * * the static lower bound, `MAX_N_CAPABILITIES`
+ * * the logical core count
+ * * the users's choice of `+RTS -N`
+ * This will serve as the upper bound on the capability count for the rest
+ * of execution. Calls to `setNumCapabilities` exceeding this bound will
+ * issue a warning and otherwise have no effect.
+ *
+ * See #25560.
+ */
+ int32_t core_count = getNumberOfProcessors();
+ if (core_count > max_n_capabilities) {
+ max_n_capabilities = core_count;
}
+ if (RtsFlags.ParFlags.nCapabilities > max_n_capabilities) {
+ max_n_capabilities = RtsFlags.ParFlags.nCapabilities;
+ }
+
+ capabilities = stgMallocBytes(sizeof(Capability) * max_n_capabilities, "initCapabilities");
+
n_capabilities = 0;
moreCapabilities(0, RtsFlags.ParFlags.nCapabilities);
n_capabilities = RtsFlags.ParFlags.nCapabilities;
=====================================
rts/Capability.h
=====================================
@@ -270,15 +270,17 @@ INLINE_HEADER void releaseCapability_ (Capability* cap STG_UNUSED,
// extern Capability MainCapability;
// declared in rts/include/rts/Threads.h:
+// extern uint32_t max_n_capabilities;
// extern uint32_t n_capabilities;
// extern uint32_t enabled_capabilities;
-// Array of all the capabilities
-extern Capability *capabilities[MAX_N_CAPABILITIES];
+// Array of all the capabilities, of size max_n_capabilities
+// See Note [Capabilities array sizing] in rts/Capability.c.
+extern Capability **capabilities;
INLINE_HEADER Capability *getCapability(uint32_t i)
{
- return RELAXED_LOAD(&capabilities[i]);
+ return RELAXED_LOAD(capabilities[i]);
}
//
=====================================
rts/RtsSymbols.c
=====================================
@@ -909,6 +909,7 @@ extern char **environ;
SymI_NeedsDataProto(rts_stop_on_exception) \
SymI_HasProto(stopTimer) \
SymI_HasProto(n_capabilities) \
+ SymI_HasProto(max_n_capabilities) \
SymI_HasProto(enabled_capabilities) \
SymI_HasDataProto(stg_traceEventzh) \
SymI_HasDataProto(stg_traceMarkerzh) \
=====================================
rts/Schedule.c
=====================================
@@ -2288,9 +2288,10 @@ setNumCapabilities (uint32_t new_n_capabilities USED_IF_THREADS)
} else if (new_n_capabilities <= 0) {
errorBelch("setNumCapabilities: Capability count must be positive");
return;
- } else if (new_n_capabilities > MAX_N_CAPABILITIES) {
- errorBelch("Attempt to increase capability count beyond MAX_N_CAPABILITIES\n");
- return;
+ } else if (new_n_capabilities > max_n_capabilities) {
+ // See Note [Capabilities array sizing] in rts/Capability.c.
+ errorBelch("setNumCapabilities: Attempt to increase capability count beyond maximum capability count %d; clamping...\n", max_n_capabilities);
+ new_n_capabilities = max_n_capabilities;
}
debugTrace(DEBUG_sched, "changing the number of Capabilities from %d to %d",
=====================================
rts/include/rts/Config.h
=====================================
@@ -79,6 +79,7 @@ code.
#if defined(THREADED_RTS)
/*
+ * See Note [Capabilities array sizing] in rts/Capability.c.
* Update the note in docs/users_guide/using-concurrent.rst when updating this.
*/
#define MAX_N_CAPABILITIES 256
=====================================
rts/include/rts/Threads.h
=====================================
@@ -77,6 +77,10 @@ INLINE_HEADER unsigned int getNumCapabilities(void)
// The number of Capabilities that are not disabled
extern uint32_t enabled_capabilities;
+// The maximum number of Capabilities supported by the RTS.
+// See Note [Capabilities array sizing] in rts/Capability.c.
+extern StgInt max_n_capabilities;
+
#if !IN_STG_CODE
extern Capability MainCapability;
#endif
=====================================
testsuite/tests/rts/T25560.hs
=====================================
@@ -0,0 +1,4 @@
+import GHC.Conc
+
+main :: IO ()
+main = setNumCapabilities 100000
=====================================
testsuite/tests/rts/T25560.stderr
=====================================
@@ -0,0 +1,3 @@
+T25560: Uncaught exception ghc-internal:GHC.Internal.IO.Exception.IOException:
+
+user error (setNumCapabilities: This GHC build only supports up to 1 capabilities)
=====================================
testsuite/tests/rts/all.T
=====================================
@@ -630,3 +630,7 @@ test('T24142', [req_target_smp], compile_and_run, ['-threaded -with-rtsopts "-N2
test('T25232', [unless(have_profiling(), skip), only_ways(['normal','nonmoving','nonmoving_prof','nonmoving_thr_prof']), extra_ways(['nonmoving', 'nonmoving_prof'] + (['nonmoving_thr_prof'] if have_threaded() else []))], compile_and_run, [''])
test('T25280', [unless(opsys('linux'),skip),req_process,js_skip], compile_and_run, [''])
+
+# N.B. This will likely issue a warning on stderr but we merely care that the
+# program doesn't crash.
+test('T25560', [normal, ignore_stderr], compile_and_run, [''])
View it on GitLab: https://gitlab.haskell.org/ghc/ghc/-/compare/df3015ce11617cf8ae20170695c299432d238295...8fdf194e19294f55802be99d65af69a224a69d35
--
View it on GitLab: https://gitlab.haskell.org/ghc/ghc/-/compare/df3015ce11617cf8ae20170695c299432d238295...8fdf194e19294f55802be99d65af69a224a69d35
You're receiving this email because of your account on gitlab.haskell.org.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.haskell.org/pipermail/ghc-commits/attachments/20241209/d10c3147/attachment-0001.html>
More information about the ghc-commits
mailing list